Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reliance or dependency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Huerta
    -0.72
    ajuato
    -0.71
    centralwidget
    -0.70
     çı
    -0.64
     Horst
    -0.62
    renta
    -0.60
    Personendaten
    -0.60
    peteer
    -0.60
     Leland
    -0.60
    trand
    -0.56
    POSITIVE LOGITS
     depend
    1.36
     depended
    1.30
     Depends
    1.29
     depends
    1.26
    depend
    1.19
    depends
    1.15
     Dependent
    1.15
     dependent
    1.15
     dependency
    1.15
    Depends
    1.13
    Act Density 0.193%

    No Known Activations